gg

scripts/audit_backtest.py

@@ -1,109 +0,0 @@
-
-import os
-import sys
-import torch
-import torch.nn.functional as F
-import pandas as pd
-import numpy as np
-
-# Path alignment
-sys.path.append(os.getcwd())
-sys.path.append(os.path.join(os.getcwd(), 'ai-engine'))
-
-from pipeline.tiered_loader import TieredDataLoader
-from pipeline.sequence_builder import SequenceBuilder
-from models.hybrid_v11 import HybridDeepModel
-from features.odds_history import OddsHistoryEngine
-from features.synthetic_xg import SyntheticXGModel
-
-DEVICE = 'cpu'
-MODEL_PATH = 'ai-engine/models/v11_hybrid_model.pth'
-TARGET_ID = 'en78ih6ec7exnpxcku3xc3das'
-
-def audit():
-    print(f"🕵️  Auditing Match: {TARGET_ID}")
-    
-    # 1. Pipeline Data
-    builder = SequenceBuilder()
-    X, y, meta = builder.build_sequences()
-    
-    # Check if target is in dataset
-    idx_list = meta.index[meta['match_id'] == TARGET_ID].tolist()
-    if not idx_list:
-        print("❌ Match not found in generated sequences. Is it too old or too new?")
-        return
-    
-    idx = idx_list[0]
-    row_meta = meta.iloc[idx]
-    
-    # 2. Features
-    loader = TieredDataLoader()
-    odds_df = loader.load_gold_data([TARGET_ID])
-    eng = OddsHistoryEngine()
-    xg_model = SyntheticXGModel()
-    
-    # Team Mapping
-    unique_teams = meta['team_id'].unique()
-    team_map = {tid: i for i, tid in enumerate(unique_teams)}
-    
-    # 3. Predict exactly like Backtest
-    state = torch.load(MODEL_PATH, map_location=DEVICE)
-    emb_key = 'entity_emb.weight' if 'entity_emb.weight' in state else 'team_embedding.weight'
-    saved_vocab_size = state[emb_key].shape[0]
-    
-    model = HybridDeepModel(num_teams=saved_vocab_size)
-    new_state = {k.replace('team_embedding', 'entity_emb'): v for k, v in state.items()}
-    model.load_state_dict(new_state, strict=False)
-    model.eval()
-    
-    # Data components
-    team_idx = team_map.get(row_meta['team_id'], 0)
-    entities = torch.LongTensor([team_idx, 0]).unsqueeze(0)
-    seq = torch.FloatTensor(X[idx]).unsqueeze(0)
-    
-    # Context (Odds + xG)
-    odds_lookup = {}
-    for _, r in odds_df.iterrows():
-        mid = r['match_id']
-        if mid not in odds_lookup: odds_lookup[mid] = {}
-        if r['category'] == 'Maç Sonucu': odds_lookup[mid][r['selection']] = r['odd_value']
-        elif r['category'] == '2,5 Alt/Üst':
-            if 'Üst' in r['selection']: odds_lookup[mid]['Over'] = r['odd_value']
-            else: odds_lookup[mid]['Under'] = r['odd_value']
-            
-    odds = odds_lookup.get(TARGET_ID, {'1': 1.0, 'X': 1.0, '2': 1.0, 'Over': 1.0, 'Under': 1.0})
-    syn_xg = 1.35 # Placeholder in trainer for xG component if used
-    hist_win_rate = eng.get_feature(row_meta['team_id'], float(odds.get('1', 1.0)))
-    
-    ctx = torch.FloatTensor([
-        float(odds.get('1', 1.0)), float(odds.get('X', 1.0)), float(odds.get('2', 1.0)),
-        float(odds.get('Over', 1.0)), float(odds.get('Under', 1.0)),
-        syn_xg, syn_xg,
-        hist_win_rate
-    ]).unsqueeze(0)
-    
-    with torch.no_grad():
-        logits_res, pred_goals, logits_btts, logits_ht_ft = model(entities, seq, ctx)
-        probs = F.softmax(logits_res, dim=1).numpy()[0]
-        prob_btts = torch.sigmoid(logits_btts).item()
-        probs_ht = F.softmax(logits_ht_ft, dim=1).numpy()[0]
-        
-    print("\n📊 INTERNAL PIPELINE PREDICTION:")
-    print(f"Target Team: {row_meta['team_id']}")
-    print(f"1X2 Probs: Home:{probs[0]:.4f} Draw:{probs[1]:.4f} Away:{probs[2]:.4f}")
-    print(f"BTTS Prob: {prob_btts:.4f}")
-    
-    ht_map = ["1/1", "1/X", "1/2", "X/1", "X/X", "X/2", "2/1", "2/X", "2/2"]
-    top3_ht = np.argsort(probs_ht)[-3:][::-1]
-    print("Top 3 HT/FT:")
-    for idx_ht in top3_ht:
-        print(f"  {ht_map[idx_ht]}: {probs_ht[idx_ht]:.4f}")
-    
-    actual_res = y[idx][0]
-    actual_ht_idx = int(y[idx][3])
-    print(f"\n✅ ACTUAL REALITY:")
-    print(f"Result (Y): {actual_res} (0.0=Away)")
-    print(f"HT/FT Class: {actual_ht_idx} ({ht_map[actual_ht_idx]})")
-
-if __name__ == "__main__":
-    audit()

scripts/test_surprise_detection.py

@@ -1,58 +0,0 @@
-#!/usr/bin/env python3
-"""Test surprise detection on known surprise matches."""
-
-import sys
-sys.path.insert(0, 'ai-engine')
-from services.single_match_orchestrator import SingleMatchOrchestrator
-import json
-
-# Test Bayern vs Augsburg (24 Jan 2026) - 1/2 Reversal
-match_id = 'en78ih6ec7exnpxcku3xc3das'
-
-orch = SingleMatchOrchestrator()
-result = orch.analyze_match(match_id)
-
-if result:
-    print('=== Bayern Munch vs Augsburg (24 Jan 2026) ===')
-    print('Actual: HT 1-0, FT 1-2 (1/2 Reversal!)')
-    print()
-    
-    # Check risk
-    risk = result.get('risk', {})
-    print(f"Risk Level: {risk.get('level', 'N/A')}")
-    print(f"Is Surprise Risk: {risk.get('is_surprise_risk', False)}")
-    print(f"Surprise Type: {risk.get('surprise_type', 'N/A')}")
-    print(f"Risk Score: {risk.get('score', 'N/A')}")
-    print()
-    
-    # Check HT/FT probabilities from market_board
-    htft = result.get('market_board', {}).get('HTFT', {}).get('probs', {})
-    print('HT/FT Probabilities:')
-    if htft:
-        for k, v in sorted(htft.items(), key=lambda x: x[1], reverse=True):
-            print(f"  {k}: {v*100:.1f}%")
-    else:
-        print("  EMPTY!")
-    print()
-    
-    # Check main pick
-    main = result.get('main_pick', {})
-    print(f"Main Pick: {main.get('market', 'N/A')} - {main.get('pick', 'N/A')}")
-    print(f"Confidence: {main.get('calibrated_confidence', 'N/A')}%")
-    print(f"Is Guaranteed: {main.get('is_guaranteed', False)}")
-    print()
-    
-    # Check aggressive pick
-    agg = result.get('aggressive_pick', {})
-    if agg:
-        print(f"Aggressive Pick: {agg.get('market', 'N/A')} - {agg.get('pick', 'N/A')}")
-        print(f"Odds: {agg.get('odds', 'N/A')}")
-    print()
-    
-    # Check bet_summary for HTFT
-    bet_summary = result.get('bet_summary', [])
-    for bet in bet_summary:
-        if bet.get('market') == 'HTFT':
-            print(f"HTFT Bet: {bet}")
-else:
-    print('Match not found')

scripts/test_surprise_improvements.py

@@ -1,95 +0,0 @@
-#!/usr/bin/env python3
-"""Test the improved surprise detection logic"""
-
-import sys
-sys.path.insert(0, 'ai-engine')
-
-from core.calculators.risk_assessor import RiskAssessor
-from config.config_loader import get_config
-
-def test_surprise_detection():
-    config = get_config()
-    assessor = RiskAssessor(config)
-    
-    # Test cases based on real scenarios
-    test_cases = [
-        {
-            'name': 'Bayern vs Augsburg (1.30 odds, 2% 1/2 prob)',
-            'odds': {'ms_h': 1.30, 'ms_d': 5.00, 'ms_a': 8.00},
-            'ht_ft': {'1/1': 0.30, '1/X': 0.07, '1/2': 0.02, 'X/1': 0.15, 'X/X': 0.16, 'X/2': 0.09, '2/1': 0.03, '2/X': 0.04, '2/2': 0.14},
-            'expected_surprise': True,
-            'expected_type': '1/2 Potential Upset'
-        },
-        {
-            'name': 'Strong favorite (1.20 odds, 1.5% 1/2 prob)',
-            'odds': {'ms_h': 1.20, 'ms_d': 6.00, 'ms_a': 12.00},
-            'ht_ft': {'1/1': 0.35, '1/X': 0.05, '1/2': 0.015, 'X/1': 0.20, 'X/X': 0.15, 'X/2': 0.05, '2/1': 0.02, '2/X': 0.03, '2/2': 0.10},
-            'expected_surprise': True,
-            'expected_type': '1/2 Potential Upset'
-        },
-        {
-            'name': 'Moderate favorite (1.50 odds, 3% 1/2 prob)',
-            'odds': {'ms_h': 1.50, 'ms_d': 4.00, 'ms_a': 6.00},
-            'ht_ft': {'1/1': 0.28, '1/X': 0.08, '1/2': 0.03, 'X/1': 0.18, 'X/X': 0.15, 'X/2': 0.08, '2/1': 0.04, '2/X': 0.05, '2/2': 0.11},
-            'expected_surprise': True,
-            'expected_type': '1/2 Potential Upset'
-        },
-        {
-            'name': 'Even match (2.00 odds, 5% 1/2 prob)',
-            'odds': {'ms_h': 2.00, 'ms_d': 3.30, 'ms_a': 3.30},
-            'ht_ft': {'1/1': 0.20, '1/X': 0.10, '1/2': 0.05, 'X/1': 0.15, 'X/X': 0.15, 'X/2': 0.10, '2/1': 0.05, '2/X': 0.10, '2/2': 0.10},
-            'expected_surprise': False,  # No clear favorite
-            'expected_type': None
-        },
-        {
-            'name': 'Away favorite (1.40 away odds, 2% 2/1 prob)',
-            'odds': {'ms_h': 6.00, 'ms_d': 4.00, 'ms_a': 1.40},
-            'ht_ft': {'1/1': 0.10, '1/X': 0.05, '1/2': 0.04, 'X/1': 0.08, 'X/X': 0.15, 'X/2': 0.20, '2/1': 0.02, '2/X': 0.06, '2/2': 0.30},
-            'expected_surprise': True,
-            'expected_type': '2/1 Potential Upset'
-        },
-    ]
-    
-    print("=" * 70)
-    print("SURPRISE DETECTION TEST RESULTS")
-    print("=" * 70)
-    
-    passed = 0
-    failed = 0
-    
-    for tc in test_cases:
-        class MockCtx:
-            is_surprise = False
-            is_top_league = True
-            sport = 'football'
-            xgboost_preds = {'ht_ft': tc['ht_ft']}
-            odds_data = tc['odds']
-        
-        result = assessor.assess_risk(MockCtx())
-        
-        # Check if result matches expectation
-        is_correct = result.is_surprise_risk == tc['expected_surprise']
-        if tc['expected_type'] and result.surprise_type != tc['expected_type']:
-            is_correct = False
-        
-        status = "✅ PASS" if is_correct else "❌ FAIL"
-        if is_correct:
-            passed += 1
-        else:
-            failed += 1
-        
-        print(f"\n{status} - {tc['name']}")
-        print(f"  Expected: surprise={tc['expected_surprise']}, type={tc['expected_type']}")
-        print(f"  Got:      surprise={result.is_surprise_risk}, type={result.surprise_type}")
-        if result.reasons:
-            print(f"  Reasons: {result.reasons}")
-    
-    print("\n" + "=" * 70)
-    print(f"SUMMARY: {passed} passed, {failed} failed")
-    print("=" * 70)
-    
-    return failed == 0
-
-if __name__ == "__main__":
-    success = test_surprise_detection()
-    sys.exit(0 if success else 1)

scripts/test_upset_engine.py

@@ -1,65 +0,0 @@
-#!/usr/bin/env python3
-"""Test UpsetEngine on Bayern vs Augsburg match."""
-
-import sys
-sys.path.insert(0, 'ai-engine')
-from features.upset_engine import get_upset_engine
-from data.db import get_clean_dsn
-import psycopg2
-from psycopg2.extras import RealDictCursor
-from datetime import datetime
-
-# Get match data
-conn = psycopg2.connect(get_clean_dsn())
-cur = conn.cursor(cursor_factory=RealDictCursor)
-
-cur.execute("""
-SELECT m.id, m.home_team_id, m.away_team_id, m.score_home, m.score_away, 
-       m.ht_score_home, m.ht_score_away, m.mst_utc,
-       th.name as home_name, ta.name as away_name, l.name as league
-FROM matches m
-JOIN teams th ON m.home_team_id = th.id
-JOIN teams ta ON m.away_team_id = ta.id
-JOIN leagues l ON m.league_id = l.id
-WHERE m.id = 'en78ih6ec7exnpxcku3xc3das'
-""")
-match = cur.fetchone()
-conn.close()
-
-if match:
-    print('=== Bayern Munch vs Augsburg (24 Jan 2026) ===')
-    print(f"Actual: HT {match['ht_score_home']}-{match['ht_score_away']}, FT {match['score_home']}-{match['score_away']} (1/2 Reversal!)")
-    print()
-    
-    # Test UpsetEngine
-    engine = get_upset_engine()
-    
-    # Calculate upset potential using get_features
-    result = engine.get_features(
-        home_team_name=match['home_name'],
-        home_team_id=match['home_team_id'],
-        away_team_name=match['away_name'],
-        league_name=match['league'],
-        home_position=1,  # Bayern is typically top
-        away_position=15,  # Augsburg is typically lower
-        match_date_ms=match['mst_utc'],
-        total_teams=18,
-    )
-    
-    print('UpsetEngine Results:')
-    print(f"  Atmosphere Score: {result.get('upset_atmosphere', 0):.2f}")
-    print(f"  Motivation Score: {result.get('upset_motivation', 0):.2f}")
-    print(f"  Fatigue Score: {result.get('upset_fatigue', 0):.2f}")
-    print(f"  Historical Score: {result.get('upset_historical', 0):.2f}")
-    print(f"  TOTAL UPSET POTENTIAL: {result.get('upset_potential', 0):.2f}")
-    print()
-    
-    # Check if upset was detected
-    if result.get('upset_potential', 0) > 0.5:
-        print("🔥 HIGH UPSET POTENTIAL DETECTED!")
-    elif result.get('upset_potential', 0) > 0.3:
-        print("⚠️ MEDIUM UPSET POTENTIAL")
-    else:
-        print("❌ LOW UPSET POTENTIAL - Model did not detect this as upset")
-else:
-    print('Match not found')